Dynamically providing to a person feedback pertaining to utterances spoken or sung by the person

Utterances spoken or sung by a first person can be received, in real time, from a mobile communication device. A location of the mobile communication device can be determined to be in an area designated as a quiet zone. A key indicator that indicates at least one characteristic of the detected utterances spoken or sung by the first person can be generated. Based, at least in part, on the key indicator, a determination can be made that the first person is speaking or singing too loudly in the area designated as the quiet zone. Responsive to determining that the first person is speaking or singing too loudly in the area designated as the quiet zone, feedback indicating that the first person is speaking or singing too loudly in the area designated as the quiet zone can be communicated to the mobile communication device.